Time series are data observed over time (either in continuous time or at discrete time periods).

learn more… | top users | synonyms

3
votes
1answer
53 views

Are log difference time series models better than growth rates?

Often I see authors estimate a "log difference" model, e.g. $\log (y_t)-\log(y_{t-1}) = \log(y_t/y_{t-1}) = \alpha + \beta x_t$ I agree this is appropriate to relate $x_t$ to a percentage change in $...
0
votes
1answer
52 views

When to use ANN with tensorflow?

I'm new to machine learning and tensorflow and I'm confused as to why (and when) to use the types of ANN (ie recurrent neural network) with tensorflow? I know RNN is good for sequences of data/time ...
0
votes
0answers
11 views

Simulating an alternative local linear model

I want to simulate an $y_{t}$ time series like this: \begin{align} y_{t} &= \mu_{t} + \epsilon_{t} \\ \mu_{t} &= \mu_{t-1}^{1+v_{t}} + \eta_{t} \\ v_{t} &= 0.7v_{t-1}+ \gamma_{t} \...
0
votes
1answer
38 views

Is this an SARIMA(0,0,0)x(0,1,4)_12?

I found someone's quick-and-dirty forecast of a variable $x$: $$\hat{x}_t = x_{t-12} + \frac{1}{4}\Delta_{12}\left(x_{t-1} + x_{t-2} + x_{t-3} + x_{t-4} \right)$$ Can this be viewed as an "optimal" ...
1
vote
0answers
17 views

Pandas Time Series DataFrame Missing Values

I have a dataset of Total Sales from 2008-2015. I have an entry for each day, and so I have a created a pandas DataFrame with a ...
1
vote
1answer
31 views

Represent Email data with respect to time

I have a bunch of problem tickets that have activity logs in the form of Email-Outbound and Email-Inbound. Outbound is an email sent and inbound is an email received. I want to identify the pain ...
0
votes
0answers
30 views

Correlation with seasonal data

I've got 5+ years of data, with multiple observations per week. I'd like to understand if there is a correlation between my dependent and independent variables. The catch is that I know this data is ...
0
votes
0answers
10 views

Dataframes of different lengths [migrated]

I'm looking at the time series of the DJIA and FSTE100 but they are not of the same length because of trading days. How can I fix this in R? I saw a code snippet and I tried to adapt it must my data ...
0
votes
2answers
50 views

Covariance Matrix for Time Series

I'm trying to investigate how events affect the stock market through econo-physics and I came across a paper that uses the co-variance matrix. What I don't understand is how such a matrix can be ...
0
votes
1answer
49 views
1
vote
1answer
61 views

How to deal with hourly non-stationary time series data with multi-seasonality?

I currently have hourly electricity demand data last for 5 years, where I used: demand <- msts(mydata$DEMAND,seasonal.period=c(24,182.5*24,365*24),start=2012) ...
0
votes
0answers
16 views

References: Association Rules + Forecasting

I am looking for any kind of information which involve Association Algorithms and forecasting. To make my point clear; let's ...
2
votes
0answers
21 views

VAR model with different time period for each series

I am trying to fit a Vector Autoregression model to forecast GDP growth Rate. I have 2 series, monthly GDP growth rate and a monthly economic indicator. For the monthly GDP growth rate, the latest ...
0
votes
0answers
6 views

How to split data for LSTM prediction of a vector?

I'm trying to decide how to best split my data to train a LSTM to predict the next time series vector, currently my inputs are 255,30 . So 255 time steps with each containing a vector of length 30 ...
0
votes
0answers
26 views

Difference between particle filter (PF) and recurrent neural network (RNN) for time series

Both method are used to estimate time series from data. The question is, when should I use one method or other? Is any advantage to use one instead of the other? I know that in a PF there is a hidden ...
0
votes
0answers
9 views

How to compare ordinal variables across groups and time?

I have a short survey that is administered twice (baseline and follow-up, same questions) to a treatment and comparison group. It contains mainly ordinal variables. Here is one example: Overall, how ...
2
votes
1answer
21 views

X13 Arima with negative values

I'm running x13 Arima analysis on a US GDP series to get the "trend" component. ...
0
votes
1answer
30 views

trade off between stationary and seassonal time series

I have the annual change in natural logs of house prices as my monthly series. When I undertake the augmented Dickey-Fuller test I observe that is not stationary, and when I plot the auto-correlation ...
0
votes
0answers
27 views

Why is prewhitening important?

I am writing code,geophysical time series processing.First step is to prewhiten values in time domain.Why is this step important? For example,I have found this on sas.com If, as is usually the case, ...
1
vote
2answers
26 views

Forecasting ranges for multiple observations with quarterly data

I have 90 markets with quarterly results, with data from 2014 Q1 to 2016 Q2. I'd like to predict 2016 Q4 results. With a time-series in R, as I understand, you need a single observation over multiple ...
1
vote
2answers
58 views

Time series with 24 yearly data points - advice needed

I have a dataset containing the prevalence rate of Malaria in Botswana, starting in 1990 and ending in 2014. My task is to verify whether these data can be used in order to make predictions on the ...
0
votes
1answer
43 views

What can I conclude from the following Granger causality test?

I have two monthly time series: one for house prices expressed in annual change growth rates: $\left( \text{ln}(X_t) - \text{ln}(X_{t-12})\right) - \left( \text{ln}(X_{t-1}) - \text{ln}(X_{t-1-12})\...
0
votes
1answer
38 views

State-of-the-art methods for forecasting time series array

Suppose I have a set of measurements taken at regular intervals, and I want to predict future values of one of those measurements. There are relationships between the variables being measured. For ...
1
vote
0answers
20 views

Time series cross-validation, calculate RMSE for different forecasting horizions

Following Rob J. Hyndman suggestions on how to do cross validation for time series ( http://robjhyndman.com/hyndsight/tscvexample/ ), I modified his original code to evaluate how RMSE (not MAE) ...
0
votes
0answers
22 views

Generating smooth time series

I want to create a smooth time series that follows a non-linear simple model, for example something like this: $Y_{t} = 0.5(Y_{t-1})^{3/2} + \epsilon_{t}$. The important part to me is to have $Y_{t-...
0
votes
0answers
13 views

changepoint detection and its analysis

I applied changepoint detection provided by ecp package against a given time series. The time series plot marked with identified change points is shown as follows. ...
0
votes
0answers
54 views

How to model really rare events in a single time-series

The event of interest happened only 5 times in the last 4 years. My independent variables are the number of results returned by Google Search for specific keywords over time (and per domain of each ...
1
vote
3answers
73 views

Model/explain a time series as a function of other time series - R

I have six time series, all made of daily historical data. All of them cover the same period and the same days, they are all about 2700 days long. I want to explain one of the time series as a ...
0
votes
0answers
17 views

Year effects in fixed effects regression

Could explain me how the interpretation of the coefficients changes when I have not only group effects (one way fixed effect model) but also time/year effects (two way year effects)? I am studying ...
3
votes
0answers
29 views

Parameter estimation for ARIMA around a complicated deterministic mean

Currently, I am trying to fit a time series to the following model: $$ (1-\phi_1B-...-\phi_3B^3)(y_t-\mu_t)=\varepsilon_t(1-\theta_1B-...-\theta_3B^3), $$ where $t=1,\dotsc,n$ and $y_t-\mu_t$ is ...
0
votes
0answers
59 views

Demand Forecasting Models

I want to forecast demand of various products using time series data of 2 years (using loops on products in R), frequency is daily and demand is to be forecasted for next 90 days I have used the ...
1
vote
0answers
20 views

Choosing between ets or arima model

I have a time series and two models to choose from: ETS and ARIMA. I have used the MAE to select a model. But when forecasting the time series and comparing the models, I don't know which model ...
1
vote
0answers
32 views

Studying fluctuations in time series

I have some time series to analyze. Given the domain the data is coming from - Time series is supposed to have some fluctuations. A regular periodicity might not be present at all in some cases. ...
1
vote
0answers
40 views

Dimensionality reduction for multivariate time series

I have a data set including 25 variables $(x_{1,t},\dotsc,x_{25,t})$ at each time $t$ and all of this group is repeated through time. I want to explore the relationship between these variables through ...
0
votes
1answer
24 views

Applying bayesian inference to a time based problem

I have a N*M matrix with N customers and M products. Each row of this matrix is a M dimensional vector like [1 3 4 1 5 ....] where each value represents how many times that customer has chosen this ...
2
votes
1answer
47 views
1
vote
0answers
16 views

Time Series: How to Deal With Differences In Public Holidays?

I am conducting analysis on the relationship between stock markets in regions with differences in the date of public holidays. That is, in some countries, Friday and Saturday are public holidays while ...
0
votes
0answers
3 views

Stacking time series data vertically [migrated]

I am struggling with manipulation of time series data. The dataset has first Column containing information about time points of data collection, 2nd column onwards contains data from different studies....
2
votes
2answers
43 views

Difference between Granger Causality and AR1

Here are my questions: is there a difference between "VAR(1)" and "AR(1)"? Granger Causality inspects the direction of causality. In return, we receive a p-value on how much a time series is likely ...
0
votes
0answers
14 views

How to calculate first order autocovariance in AR(1) process?

For a process describing dividend yield $x_t$, it is assumed to follow a first-order autoregressive process: $ x_t=\delta +\phi x_{t-1} + \eta_t $ where $|\phi|<1$ and $\eta \sim \mathcal{N}(0,\...
1
vote
1answer
68 views

RNN learning sine waves of different frequencies

As a warm up with recurrent neural networks, I'm trying to predict a sine wave from another sine wave of another frequency. My model is a simple RNN, its forward pass can be expressed as follow: $$ \...
0
votes
0answers
11 views

Given Three Time Series Estimate a Fourth

I have three time series $Y^{1,2,3}$ that I expect to vary according to some parameter that modulates the amplitude for a specific window. How can I estimate a fourth time-series based on their ...
5
votes
5answers
149 views

What is the best way to detect repetition in xyz data for purposes of splitting data?

I'll use this picture to explain What I want to do is define some patterns as trained patterns. Then given data I want to be able to determine if the pattern exists in the dataset, and if it does ...
3
votes
0answers
45 views

Perceptron trained on time series always predicting the same answer

Using the model from theano's tutorial, I'm training a 3-layers perceptron with log returns over a very large dataset (~55,000 points). The output's layer contains two neurons, one for each of the ...
3
votes
0answers
42 views

K-fold cross-validation for time series with dynamic target variable (Scikit)

I would like to do a K-fold cross-validation on time series data (market data) with a two class classification target. My test folds must be forward looking and of a fixed size ...
0
votes
0answers
20 views

Raster time series smoothing

I'm searching for an R package to raster time series smoothing. Currently, I'm using an approach like this one (using the equation suggested by Hamunyella et al., 2013) ...
1
vote
0answers
35 views

Strong fluctuations in level component after TBATS

I have 2 time series sampled at a weekly level spanning a period from the start of 2010 until the present. Initially I had used a TBATS model with the frequency of the time series set to ...
0
votes
0answers
19 views

Portmanteau Test for Cross Correlations

How can I test for the joint significance of cross-correlations between two variables? Suppose I have two stocks. I wish to test if they are related to each other non-contemporaneously (i.e. have some ...
0
votes
1answer
25 views

Timeseries with binary regressors

I'm trying to identify impact of some causal events on a given timeseries. However, the trouble is I only know whether the event occurred or not (binary). What kind of techniques can I use to create ...
0
votes
0answers
17 views

HMM for fitting multiple time series with covariates

I have a large number of possibly correlated time series with multiple covariates that have the potential to affect them all. I'd like to approach them using HMM but I am not sure about the following:...